Speecht5 Tts

Downloads
Hugging Face
1.5M
HF Likes
Hugging Face
33
Context
Small context
600
License
—
Updated
11/3/2025
by
Xenova

Base model for text-to-speech using the SpeechT5 architecture from Microsoft, implemented in the transformers.js library.

Audio Model
OTHER
Try on Hugging Face
Add to Compare

Quick Info

Released
9/21/2023
Framework
OTHER

Resources

Training Data Analysis

🔵 Good (6.0/10)

Researched training datasets used by Speecht5 Tts with quality assessment

Specialized For

general
multilingual

Training Datasets (1)

c4
🔵 6/10
general
multilingual
Key Strengths
  • •Scale and Accessibility: 750GB of publicly available, filtered text
  • •Systematic Filtering: Documented heuristics enable reproducibility
  • •Language Diversity: Despite English-only, captures diverse writing styles
Considerations
  • •English-Only: Limits multilingual applications
  • •Filtering Limitations: Offensive content and low-quality text remain despite filtering

Explore our comprehensive training dataset analysis

View All Datasets